[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117759-en":3,"doc-seo-117759-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":21,"html_lang":23,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},117759,1099513958762,"Logic","https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1784791008015729253",8,"Research & Report","Machine Learning Model for Repurposing Drugs to Target Viral Diseases - thesis","Recent outbreaks such as the Covid-19 pandemic increase the urgency of strategies to combat viral diseases. Advances in computer-aided drug design and machine learning (ML) have boosted hit identification, enabling both discovery of novel scaffolds and repurposing of existing therapeutics. This thesis improves non-binding data selection in antiviral classification models by training a fingerprint-based classifier on randomly selected versus rationally selected non-binding datasets. A combined XGBoost, Random Forest, and SVM workflow predicts SARS-CoV-2 Mpro inhibitors, and structure-based analyses refine top ranked hits using AutoDock Vina and MMGBSA from molecular dynamics.","Machine Learning Model for Repurposing Drugs to Target Viral Diseases  \nby  \nJustine Williams  \nA thesis  \npresented to the University of Waterloo in fulfillment of the  \nthesis requirement for the degree of  \nMaster of Science  \nin  \nChemistry  \nWaterloo, Ontario, Canada, 2023  \n© Justine Williams 2023  \nAuthor’s Declaration  \nI hereby declare that I am the sole author of this thesis. This is a true copy of the thesis, including any required final revisions, as accepted by my examiners.  \nI understand that my thesis may be made electronically available to the public.  \nAbstract  \nWith recent events, such as the Covid-19 pandemic, it is increasingly important to develop strategies to combat viral diseases. Due to technological advancements, computer-aided drug design and machine learning (ML)-based hit identification strategies have gained popularity. Applying these techniques to identify novel scaffolds and/or repurpose existing therapeutics for viral diseases is a promising approach. As an avenue to improve existing classification models for antiviral applications, this thesis aimed to make improvements to non-binding data selection within these models. We created a classification model using molecular fingerprints to assess the performance of machine learning predictions when the model is trained using randomly selected and rationally selected non-binding datasets. Our analyses revealed that machine learning predictions can be improved using a rational selection approach. We further used this approach and trained three machine learning models based on XGBoost, Random Forest, and Support Vector Machine to predict potential inhibitors for the SARS-CoV2 main protease (Mpro) enzyme. Probability-ranked hits from the combined model were further analyzed using classical structure-based methods. The binding modes and affinities of the hits were identified using AutoDock Vina, and molecular dynamics simulations-enabled MMGBSA calculations. The top hits identified from this multi-step screening approach revealed potential candidates that show improved affinity and stability than existing non-covalent Mpro inhibitors. Thus, our approach and the model could be useful for screening large ligand libraries.  \nAcknowledgements  \nI would like to thank my supervisor, Dr. Subha Kalyaanamoorthy, for her guidance and support throughout my studies, as well as the other members of the SK lab.  \nTable of Contents  \nAuthor’s Declaration................................................................................................................. ii  \nAbstract .................................................................................................................................... iii  \nAcknowledgements .................................................................................................................. iv  \nList of Figures ......................................................................................................................... vii  \nList of Tables ........................................................................................................................... ix  \nChapter 1 Introduction .............................................................................................................. 1  \nChapter 2 Methods .................................................................................................................... 5  \n2.1 Datasets ........................................................................................................................... 5  \n2.1.1 Binding Information ................................................................................................. 5  \n2.1.2 Small Molecule Screening Libraries ........................................................................ 7  \n2.1.3 Molecular Representations and Similarity Indices ................................................... 8  \n2.2 Machine Learning Methods ..............................................","cbCaif9NBdQ9U2kP","https://ap.wps.com/l/cbCaif9NBdQ9U2kP","pdf",6290099,1,105,"English","en","# Abstract\n# Acknowledgements\n# Chapter 1 Introduction\n# Chapter 2 Methods\n## Datasets\n## Machine Learning Methods\n## Additional Computational Analysis Methods\n# Chapter 3 Classification Model\n## DUD-E Fingerprint Screening\n## Classification Model Refinement\n# Chapter 4 Structure-Based Analysis","[{\"question\":\"What problem does the thesis address in antiviral machine learning models?\",\"answer\":\"It targets improving classification performance by refining how non-binding datasets are selected for antiviral applications.\"},{\"question\":\"How does the thesis build and evaluate the classification model?\",\"answer\":\"It trains a molecular-fingerprint-based classifier using non-binding datasets chosen either randomly or rationally, then compares prediction performance.\"},{\"question\":\"How are predicted SARS-CoV-2 Mpro inhibitors validated and prioritized?\",\"answer\":\"Top hits from an ensemble of ML models are analyzed using structure-based screening with AutoDock Vina for binding modes and molecular dynamics-driven MMGBSA for binding free energy and stability.\"}]","Machine Learning Model for Repurposing Drugs to Target Viral Diseases - thesis | PDF",1785679424,265,{"code":4,"msg":30,"data":31},"ok",{"site_id":21,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"machine-learning-model-for-repurposing-drugs-to-target-viral-diseases-thesis","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/machine-learning-model-for-repurposing-drugs-to-target-viral-diseases-thesis/117759/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does the thesis address in antiviral machine learning models?","Question",{"text":74,"@type":75},"It targets improving classification performance by refining how non-binding datasets are selected for antiviral applications.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does the thesis build and evaluate the classification model?",{"text":79,"@type":75},"It trains a molecular-fingerprint-based classifier using non-binding datasets chosen either randomly or rationally, then compares prediction performance.",{"name":81,"@type":72,"acceptedAnswer":82},"How are predicted SARS-CoV-2 Mpro inhibitors validated and prioritized?",{"text":83,"@type":75},"Top hits from an ensemble of ML models are analyzed using structure-based screening with AutoDock Vina for binding modes and molecular dynamics-driven MMGBSA for binding free energy and stability.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":21},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]